Gclaw is a Gcore-hosted, fully managed version of OpenClaw with built-in inference powered by Gcore GPU infrastructure. It allows launching an AI agent instantly without setting up infrastructure, managing tokens, or configuring providers.Documentation Index
Fetch the complete documentation index at: https://gcore.com/docs/llms.txt
Use this file to discover all available pages before exploring further.
Capabilities
With Gclaw:- A ready-to-use AI agent launches in seconds.
- Interaction occurs through a chat interface.
- Integrations such as Telegram and Discord can be connected.
- Built-in skills for development, productivity, and automation are available.
Getting started
To launch an instance and begin using Gclaw, follow the steps in the Getting started guide.Security model
Gclaw runs each instance in an isolated environment. The OpenClaw agent has system-level access to the instance and executes commands based on prompts. For details about isolation, risks, and responsibilities, see the Security model documentation.Integrations and skills
Gclaw includes built-in skills and supports external integrations.- To view available skills, ask the assistant directly in the chat.
- To configure integrations and API keys, see the API key configuration guide.
Limits and pricing
- Model limits and quotas: see the Limits and quotas guide.
- Pricing details: see the Pricing page.
Support
Gcore provides support for infrastructure and billing issues. For OpenClaw-specific questions, refer to the official OpenClaw documentation.| Issue type | Gcore support |
|---|---|
| Service down or 500 errors | Yes |
| Billing and subscription issues | Yes |
| OpenClaw usage questions | No - refer to OpenClaw docs |
| Feature requests | Logged for consideration |